#131: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Apr 23, 2024•31 min
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
CUDA で書かれた PyTorch 用カーネルに森田が玉砕しました。
For the best experience, listen in Metacast app for iOS or Android